Date Approved


Embargo Period


Document Type


Degree Name

MS Electrical and Computer Engineering


Electrical & Computer Engineering


Henry M. Rowan College of Engineering


Polikar, Robi

Committee Member 1

Bouaynaya, Nidhal

Committee Member 2

Baliga, Ganesh


algorithms, cortical learning algorithm, hierarchical temporal memory, machine learning, neural network, neuroscience


Artificial intelligence; Neocortex


Electrical and Computer Engineering | Neuroscience and Neurobiology


Pattern recognition and machine learning fields have revolutionized countless industries and applications from biometric security to modern industrial assembly lines. The fields continue to accelerate as faster, more efficient processing hardware becomes commercially available. Despite the accelerated growth of the pattern recognition and machine learning fields, computers still are unable to learn, reason, and perform rudimentary tasks that humans and animals find routine. Animals are able to move fluidly, understand their environment, and maximize their chances of survival through adaptation - animals demonstrate intelligence. A primary argument in this thesis that we have not yet achieved a level of intelligence similar to humans and animals in the pattern recognition and machine learning fields, not due to a lack of computational power but, rather, due to lack of understanding of how the cortical structures of mammalian brain interact and operate.

This thesis describes a cortical learning algorithm (CLA) that models how the cortical structures in the mammalian neocortex operate. Furthermore, a high level understanding of how the cortical structures in the mammalian brain interact, store semantic patterns, and auto-recall these patterns for future predictions are discussed. Finally, we demonstrate that the algorithm can build and maintain a model of its environment and provide feedback for actions and/or classification in a similar fashion to our understanding of cortical operation.